Skip to content

Parsa-29/loop-config / skills/linear-agent-workflow

linear-agent-workflow

Verified

Use when coding from Linear issues, syncing task status, creating implementation plans, posting progress comments, or linking GitHub PRs.

FileKindSize
SKILL.mdskill md2.3 KB
---
name: linear-agent-workflow
description: Use when coding from Linear issues, syncing task status, creating implementation plans, posting progress comments, or linking GitHub PRs.
---

# Linear Agent Workflow

Use Linear as the task context and status surface for coding work.

## When to Use

Use this skill when the user:
- Provides a Linear issue ID or project name.
- Asks what to work on next.
- Asks to sync task status, post progress, or link a GitHub PR.
- Mentions Linear-backed coding, agent task management, worktrees, branches, forks, or PR handoff.

## Workflow

1. Fetch Linear context first.
   - Read the issue or project before inspecting code when the task starts from Linear.
   - Treat title, description, comments, labels, status, linked PRs, assignee, priority, cycle, and project as task context.

2. Plan before non-trivial work.
   - For multi-file, risky, or ambiguous changes, post a short implementation plan as a Linear comment.
   - Include intended files/modules, verification commands, risks, and blockers.

3. Keep status aligned.
   - Move to `In Progress` when implementation starts.
   - Move to `In Review` when a PR exists or the diff is review-ready.
   - Move to `Blocked` when credentials, approvals, CI, environment, or product decisions are missing.

4. Report completion in Linear.
   - Comment with summary, changed files, verification output, unresolved risks, and PR link if available.
   - Do not mark complete unless the requested done condition is satisfied.

## Guardrails

- Do not create or update Linear issues unless the user asked or provided an issue ID.
- Do not invent issue IDs, team names, labels, projects, statuses, or PR URLs.
- Read before write: list/fetch Linear entities before mutating them.
- If Linear tools are unavailable or auth fails, tell the user exactly what failed and continue with local work only if the task has enough context.
- Git push, deploys, DB writes/migrations, dependency additions, secret edits, and live external mutations still require human approval.

## Suggested Linear Comment Shapes

Plan comment:
```md
Plan:
- Scope: ...
- Files/modules: ...
- Verification: ...
- Risks/blockers: ...
```

Completion comment:
```md
Done:
- Summary: ...
- Changed files: ...
- Verification: ...
- PR: ...
- Remaining risks: ...
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall